Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1316379 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0767. Min Act: -0.0002

Data Index: 818459 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0738. Min Act: -0.0002

Data Index: 960649 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0698. Min Act: -0.0002

Data Index: 140000 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0697. Min Act: -0.0002

Data Index: 539882 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0680. Min Act: -0.0002

Data Index: 236042 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0603. Min Act: -0.0002

Data Index: 106378 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0647. Min Act: -0.0002

Data Index: 670546 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0568. Min Act: -0.0002

Data Index: 213715 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0585. Min Act: -0.0002

Data Index: 710649 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1005590 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0567. Min Act: -0.0002

Data Index: 86632 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0578. Min Act: -0.0002

Data Index: 424942 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0547. Min Act: -0.0002

Data Index: 339868 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0569. Min Act: -0.0002

Data Index: 761061 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1200723 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0545. Min Act: -0.0002

Data Index: 807004 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0552. Min Act: -0.0002

Data Index: 20431 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0542. Min Act: -0.0002

Data Index: 639650 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0543. Min Act: -0.0002

Data Index: 312421 (C4 (Web Text))

Max Activating Token Index: 695